Closed AnkitaBarbora closed 1 year ago
@AnkitaBarbora - you can go ahead! We are assigning you 21 days for this project, after which it will be assigned to someone else if not completed. All the best!
Name the file as: algorithm_dataset.ipynb
and link it in the readme of the labeled directory as algorithm - dataset
.
@khusheekapoor Hello ma'am, I would like to work on the ML model as well as a deployment project for this issue so it'll be going in separate folders, shall I create separate PR for both or will it be considered under the same PR?
You have to create two separate PRs.
Okay ma'am, thank you.
Is your feature request related to a problem? Please describe.
Yes, the feature request is related to addressing the problem of hate speech and offensive language online. Hate speech and offensive language can have harmful effects on individuals and communities, contributing to discrimination, harassment, and the spread of negativity in online spaces. Therefore, the development of a machine learning-based solution for hate speech detection aims to mitigate these issues and create a safer and more inclusive online environment.
Describe the solution you'd like
The ideal solution for hate speech and offensive language detection using machine learning would involve the following components:
Describe alternatives you've considered
Rule-based systems: Instead of using machine learning algorithms, a rule-based system can be employed to detect hate speech and offensive language. This approach involves defining a set of predefined rules and patterns that indicate the presence of such language. However, rule-based systems might struggle with capturing nuanced or context-dependent expressions, and they can be less adaptable to evolving language patterns.
Additional context
Dataset to be used: https://www.kaggle.com/datasets/mrmorj/hate-speech-and-offensive-language-dataset
Code of Conduct